Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder

Documenti analoghi

• Progressive Language-guided Visual Learning for Multi-Task Visual Grounding
  di: Wang, Jingchao, et al.
  Pubblicazione: (2025)
• VPTracker: Global Vision-Language Tracking via Visual Prompt
  di: Wang, Jingchao, et al.
  Pubblicazione: (2025)
• Learning Spectral Diffusion Prior for Hyperspectral Image Reconstruction
  di: Yu, Mingyang, et al.
  Pubblicazione: (2025)
• A Simple and Better Baseline for Visual Grounding
  di: Wang, Jingchao, et al.
  Pubblicazione: (2025)
• CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation
  di: Luo, Zhuoyan, et al.
  Pubblicazione: (2024)